Agent Memory Leaderboard

The open benchmark for agent memory

Agent Memory<br>Leaderboard

Measure what your agents remember.<br>Compare what truly matters.

Start

ENEnglish<br>中中文

Slate Cool and precise

Ember Warm and editorial

Signal Bright and technical

Harbor Calm and professional

Nocturne Dark and focused

OPEN BENCHMARK

Agent Memory Leaderboard

A public benchmark space for comparing textual and coding-agent memory systems under a consistent evaluation flow.

View Leaderboard<br>Submit Evaluation Request<br>Read Documentation<br>Submit Evaluation Request

Leaderboard Preview

Textual<br>Coding

Open Full Textual Board

Benchmark Tracks

Each track keeps its own result table and detailed metric breakdown.

Textual Memory

Long-context, persona, script, and conversation-memory benchmarks.

Coding Agent Memory

Agent memory support for coding tasks and repository-context recall.

Evaluation Flow

Industry systems use the hosted Add/Search key flow. Academic systems may use the same flow or submit a public GitHub repository for maintainer Docker deployment.

1Choose an evaluation route<br>Provide hosted Add/Search APIs, or submit a public GitHub repository with Docker and API run instructions.

2Run a smoke test<br>Use the issued key to verify the synchronous Add/Search flow.

3Submit a formal evaluation<br>After smoke passes, submit the full scored evaluation.

Explore the Platform<br>Use the product pages to inspect rankings, run evaluations, and prepare an integration.

01

Leaderboard<br>Public ranking with filters, dataset columns, and score bars.

02

Evaluation<br>Create eval jobs, watch progress, and inspect private results.

03

Participation Guide<br>Eligibility, submission routes, required materials, timelines, rewards, and publication rules.

04

Documentation<br>User guide, evaluation workflow, API contract, security, and result publication.

05

Guide<br>Add/search API contract, request fields, polling, and response schemas.

OFFICIAL CHANNELS<br>Stay connected with Agent Memory Leaderboard

Follow releases, challenge updates, and participation announcements through our official channels.

Official WeChat Account Scan for the latest updates

X / Twitter@AgentMemoryL ↗<br>Contact[email protected] ↗

PUBLIC RANKINGS

Agent Memory Leaderboard

Public rankings are separated by track. Use the selector inside the leaderboard frame to switch tables without mixing metric dimensions.

Industry Board

Academic Board

Leaderboard

Textual<br>Coding

Acknowledgements<br>Thank you for making your API products available and supporting the AML evaluation!

First-cycle evaluation results will be released in mid-August.

Academic board submissions are open now. Submit your evaluation request before the first-cycle deadline.

Submit Evaluation Request

PUBLIC RANKINGS

Agent Memory Leaderboard

Public rankings are separated by track. Use the selector inside the leaderboard frame to switch tables without mixing metric dimensions.

Industry Board

Academic Board

Leaderboard

Textual<br>Coding

First-cycle evaluation results will be released in mid-August.

Academic board submissions are open now. Submit your evaluation request before the first-cycle deadline.

Submit Evaluation Request

EVALUATION

Run Evaluations

Create API-gated eval jobs against the Leaderboard Suite, monitor task progress, inspect private results, and submit eligible full-suite runs for administrator review.

Submit Evaluation Request<br>Add Version<br>View Private Results<br>API Guide

Evaluation Access

Dataset suite1

Eval modes3

FullLightSmokeScriptMem

Invitation progress<br>0 / 3 successful

0 Invited

0 Successful evaluations

Invitation code-

Create Eval Job

Choose a bound version. Use Run label to distinguish repeated evaluations of the same version.

System name<br>Version nameVerify a key to load versions<br>Modefulllightsmokescriptmem<br>Max add concurrency 16-64<br>Search concurrency 16-256<br>Top K<br>Run label

Resume latest interrupted job<br>Continue the latest interrupted evaluation from its last compatible checkpoint.

Datasets

FULL EVALUATION GATE<br>Full evaluation checklist

Confirm each item before starting a public-board candidate run. The button remains locked until every item is checked.

0 / 8 confirmed

Smoke test completed The Add/Search API has passed the platform smoke test and is currently usable.<br>API contract is followed The submitted code and deployed interfaces are wrapped according to the official Add/Search format.<br>Add/Search uses gpt-4o-mini The model used by the submitted memory system during both Add and Search must be gpt-4o-mini. The platform will reproduce the submission; if the reproduced score differs materially, the leaderboard result may be invalidated.<br>Runtime will stay stable If you provide a deployed endpoint, it will remain publicly reachable and stable for at least 30 days after submission.<br>Run instructions are complete The repository README or submission notes include the Docker command, API entrypoint, configuration, and startup steps.<br>Original work is disclosed Any...